This project was originally initiated by Dr. Negar Golestani during her time as a Ph.D. student in the MiXIL laboratory. The foundational idea was introduced in her 2017 paper, “Magnetic Induction Communications for Wireless Body Area Network”. Building on this, the 2020 publication in Nature Communications (Golestani & Moghaddam, 2020) presented a novel human activity recognition (HAR) system using magnetic induction (MI) signals and deep recurrent neural networks. This system offers a low-power, secure, and accurate alternative to conventional wearable sensors by capturing relative motion through MI-based coil networks.
Currently, the project is being extended in collaboration with the ACME Laboratory at USC, with the goal of advancing from activity recognition to full-body human motion tracking.
